Research map / Image generation / Autoregressive and latent generation
Pathological Evidence Exploration in Deep Retinal Image Diagnosis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use lesion-level pathological descriptors and a GAN conditioned on vessel segmentations | Retinal fundus synthesis · Ophthalmologist survey (560 images) | fundus realness score: 2.91 -> 4.21 | Helped |
| Use lesion-level pathological descriptors and a GAN conditioned on vessel segmentations | Retinal fundus synthesis · Ophthalmologist survey (560 images) | lesion realness score: 2.53 -> 3.37 | Helped |
| Use lesion-level pathological descriptors and a GAN conditioned on vessel segmentations | Retinal fundus synthesis · Ophthalmologist survey (560 images) | DR severity score: 2.53 -> 3.08 | Helped |
| Use the proposed descriptor-based method instead of Tub-sGAN | Retinal fundus synthesis · DRIVE | training time: 108/109 min -> 90 min | Helped |
| Use the proposed descriptor-based method instead of Tub-sGAN | Retinal fundus synthesis · DRIVE | testing time: 0.45/0.12 s -> 0.12 s | Mixed |
| Add retina detail loss (ablation) | Retinal fundus synthesis · DRIVE | physiological detail preservation | Helped |
| Add pathological loss (ablation) | Retinal fundus synthesis · DRIVE | DR detector severity score: 0 | Helped |
| Increase the weight of pathological loss (ablation) | Retinal fundus synthesis · DRIVE | DR detector severity score | Helped |
| Use retina detail loss instead of L1 loss (ablation) | Retinal fundus synthesis · DRIVE | physiological detail preservation | Helped |
Closest papers by meaning
- Vision-Language Models Guided Graph Concept Reasoning for Interpretable Diabetic Retinopathy Diagnosis (AAAI 2026 · similarity 0.88)
- FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs (NeurIPS 2026 · similarity 0.86)
- Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading (AAAI 2025 · similarity 0.86)
- HACDR-Net: Heterogeneous-Aware Convolutional Network for Diabetic Retinopathy Multi-Lesion Segmentation (AAAI 2024 · similarity 0.86)
- SIGraph: Saliency Image-Graph Network for Retinal Disease Classification in Fundus Image (AAAI 2025 · similarity 0.85)
- Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Data (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.